Sim-to-Real Reinforcement Learning for Path-Safe Target Reaching in Robotic Harvesting of Hydroponic Lettuce
Sim-to-Real Reinforcement Learning for Path-Safe Target Reaching in Robotic Harvesting of Hydroponic Lettuce
This study introduces PSA-PPO, a target-conditioned local reaching framework for robotic harvesting of hydroponic lettuce. Trained entirely in simulation, PSA-PPO achieves 94.7% reaching rate in physical testing, outperforming classical planners. The method integrates safety constraints and trajectory-based encoding to improve performance in constrained environments.
This paper presents PSA-PPO, a reinforcement learning framework for robotic harvesting of hydroponic lettuce, demonstrating high success rates in both simulation and physical testing. The method integrates safety constraints and trajectory-based encoding to improve performance in constrained environments.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- Controlled physical settingOpen source S4
Reported numbers
number of targets
150
View original evidence
arm without any real-world policy fine-tuning. In a controlled physical benchmark against 150 scheduled targets, PSA-PPO achieved the highest reaching rate of 94.7%, outperforming Cartesian+TOTG (86.0%), RRTConnect (88.0%), and RRT* (80.0%), while reducing median RMS jerk by 39.8 to 73.0% relative to the classical planners during the final approach segment. A formulation ablation evaluated over 200 simulation target
Open source S4number of harvesting attempts
144
View original evidence
sion module and an end-effector and evaluated as a complete greenhouse harvesting system across 144 lettuce harvesting attempts, achieving 94.4% vision-guided target reaching and 86.1% complete harvesting success.
Open source S6
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arm without any real-world policy fine-tuning. In a controlled physical benchmark against 150 scheduled targets, PSA-PPO achieved the highest reaching rate of 94.7%, outperforming Cartesian+TOTG (86.0%), RRTConnect (88.0%), and RRT* (80.0%), while reducing median RMS jerk by 39.8 to 73.0% relative to the classical planners during the final approach segment. A formulation ablation evaluated over 200 simulation target
Open source S4
sion module and an end-effector and evaluated as a complete greenhouse harvesting system across 144 lettuce harvesting attempts, achieving 94.4% vision-guided target reaching and 86.1% complete harvesting success.
Open source S6
s demonstrates that path-safety and side-corridor shaping are the principal drivers of harvesting-compatible performance: removing either term substantially degrades strict success even when terminal endpoint accuracy is preserved or improved, confirming that optimization toward the endpoint alone is an insufficient objective for constrained crop-proximal manipulation. Finally, PSA-PPO was integrated with an RGB-D vi
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org